ICSE 2024 (series) / GI@ICSE 2024 (series) / GI@ICSE 2024 /
Executing One’s Way out of the Chinese Room
Tue 16 Apr 2024 09:15 - 10:30 at Vianna da Motta - Opening and Keynote Chair(s): Gabin An, Aymeric Blot, Oliver Krauss, William B. Langdon, Vesna Nowack, Justyna Petke
One very attractive property of Large Language Models (LLMs) is their emergent in-context learning capability, which enables us to simply describe our requirements in natural languages and get the corresponding souce code generated in programming languages. While LLMs as a generative model are known to hallucinate, i.e., generate factually incorrect contents, the fact that code can be executed can be used to fight this phenomenon. We briefly look at existing techniques designed to improve the correctness of code generated by LLMs, and will try to imagine the future of Genetic Improvement that is supported, enhanced, and driven by LLMs.
Tue 16 AprDisplayed time zone: Lisbon change
Tue 16 Apr
Displayed time zone: Lisbon change
09:00 - 10:30 | Opening and KeynoteGI@ICSE at Vianna da Motta Chair(s): Gabin An Korea Advanced Institute of Science and Technology, Aymeric Blot University of Rennes / IRISA / INRIA, Oliver Krauss University of Applied Sciences Upper Austria, William B. Langdon University College London, Vesna Nowack Imperial College London, Justyna Petke University College London | ||
09:00 15mDay opening | Welcome and Introductions GI@ICSE | ||
09:15 75mKeynote | Executing One’s Way out of the Chinese Room GI@ICSE Shin Yoo KAIST |